Real-time defect detection using online learning for laser metal deposition

Ouidadi, Hasnaa; Guo, Shenghan; Zamiela, Christian; Bian, Linkan

doi:10.1016/j.jmapro.2023.05.030

Cited by 8 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This dataset has been adapted and utilized in several works on data-driven thermal monitoring for porosity detection [2] , [3] , [4] , [5] , [6] , [7] , [8] , [9] , [10] , [11] , online transfer learning [12] , and surrogate modeling [13] . These works aim to address quality assurance challenges by developing methods to measure statistical changes in melt pool data and characterizing relationships between thermal responses and porosity labels.…”

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

Thermal-porosity characterization data of additively manufactured Ti–6Al–4V thin-walled structure via laser engineered net shaping

Zamiela,

Tian,

Guo

et al. 2023

Data in Brief

Self Cite

View full text Add to dashboard Cite

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

Thermal-porosity characterization data of additively manufactured Ti–6Al–4V thin-walled structure via laser engineered net shaping

Zamiela,

Tian,

Guo

et al. 2023

Data in Brief

Self Cite

View full text Add to dashboard Cite

“…Machine learning algorithms, on the other hand, have emerged as powerful tools for monitoring and controlling very complex processes [22][23][24]. By leveraging the capabilities of these algorithms, it becomes possible to analyze complex and high-dimensional data acquired during the process and extract valuable insights in real-time [25]. Various machine learning techniques have been employed for process monitoring, including artificial neural networks (ANNs), support vector machines (SVMs), random forests (RFs) and convolutional neural networks (CNNs), as well as hybrid models.…”

Section: Introductionmentioning

confidence: 99%

“…Implementing semi-supervised learning techniques for label generation in model training yields cost reduction advantages [27], primarily by leveraging more affordable and widely accessible measuring equipment. Moreover, the adoption of transfer learning optimizes the model training process, requiring less data while still attaining satisfactory results [25]. This not only enhances efficiency but also contributes to overall cost reduction in the implementation of machine learning approaches.The use of semi-supervised learning with synthetic data points generated for labelling, however, is still scarce in image based machine learning techniques, specially with models that are lightweight.…”

Section: Introductionmentioning

confidence: 99%

Real-time prediction of deposited bead width in L-DED using Semi-Supervised Transfer Learning

Mochi,

Núñez,

Ribeiro

et al. 2023

Preprint

View full text Add to dashboard Cite

Laser Directed Energy Deposition (L-DED) is an additive manufacturing (AM) technology that offers unique advantages for creating and repairing metallic parts. The quality of the final print is highly dependent on the consistency of the printing parameters, and as a result, the deposited bead geometry along the printing pathway. Inconsistencies, particularly in the bead width, can produce defects between adjacent beads, increasing the material susceptibility to failure. Therefore, it is crucial to monitor and predict the printing parameters in real-time during the process. The objective of this study is to develop a machine learning model that accurately predicts the width of the deposited track in real-time. To achieve this, a dataset with approximately 12,379 melt pool images was used to train the algorithm and predict the width of the deposited track. Each one of the deposited track was measured by a profilometer at 10 points along the pathway, and intermediate labels were predicted using a spline curve, making the model semi-supervised. To implement the machine learning model, pre-trained frozen networks based on Convolutional Neural Networks (CNN) architectures VGG, ResNet, and DenseNet were employed, using transfer learning principles. These networks were integrated into a dense, fully connected network containing trainable parameters. The results demonstrate a good model fit, with a mean absolute error of 4.5% and a mean absolute error of 0.0358 mm. Moreover, the processing frequency of the best model, at 55 Hz, enables real-time control of the L-DED manufacturing process. It is important to highlight, however, that the VGG based model shows a frequency of 250 Hz and similar results. Thus, accurately predicting the width of the deposited bead has the potential to significantly improve the quality of the final part by reducing overall defects, such as lack of fusion and porosity, whenever this data is used as input to a feed-back control system. This is particularly valuable in industries where mechanical properties and fatigue life are critical, such as automotive, aerospace, and biomedical sectors. The models developed in this study offer a promising approach to effectively provide data to control the L-DED manufacturing process in real-time, enabling the reliable production of high-quality components associated with reduced manufacturing costs.

show abstract

A Comparative Study of Transfer Learning on CNN-Based Models for Fault and Anomaly Detection in Industrial Processes

Salsano,

Menanno,

Bernardi

2024

Advances and Trends in Artificial Intelligence. Theory and Applications

View full text Add to dashboard Cite

Real-time defect detection using online learning for laser metal deposition

Cited by 8 publications

References 34 publications

Thermal-porosity characterization data of additively manufactured Ti–6Al–4V thin-walled structure via laser engineered net shaping

Thermal-porosity characterization data of additively manufactured Ti–6Al–4V thin-walled structure via laser engineered net shaping

Real-time prediction of deposited bead width in L-DED using Semi-Supervised Transfer Learning

A Comparative Study of Transfer Learning on CNN-Based Models for Fault and Anomaly Detection in Industrial Processes

Contact Info

Product

Resources

About